【新人求助】换脸不成功，为什么？
本帖最后由 adobejames 于 2024-3-16 15:44 编辑请问已经把有人脸（张雨琦）放到data_src里了，为什么换脸merge的时候没有出现张雨琦的脸呢？（模型用的是RTT model 224 V2）什么原因啊？
你需要训练 张雨琦的模型，而不是 RTT model 224 V2
用张雨琦的人脸模型合成的视频才是 张雨琦的脸 ，多看下教程吧 meiyouruguo 发表于 2024-3-16 15:59
你需要训练 张雨琦的模型，而不是 RTT model 224 V2
用张雨琦的人脸模型合成的视频才是 张雨琦的脸 ，多看 ...
像换成自己脸的没找到视频教程，都是已经有专丹比如宋秩的模型，然后换好脸的就是宋秩的，我想换成张雨琦的，大大哪里有教程，最好是视频的，b站没找到 adobejames 发表于 2024-3-16 16:05
像换成自己脸的没找到视频教程，都是已经有专丹比如宋秩的模型，然后换好脸的就是宋秩的，我想换成张雨琦 ...
论坛上还是有好的模型的，多找找吧,教程的话网上很多，先学训练模型 meiyouruguo 发表于 2024-3-16 17:39
论坛上还是有好的模型的，多找找吧,教程的话网上很多，先学训练模型
好的模型能推荐下吗？ RTT model 224 V2这个吗？ 训练点击后出错了，这是什么情况？
Error: 2 root error(s) found.
(0) Resource exhausted: OOM when allocating a buffer of 205521156 bytes
[]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
[]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
(1) Resource exhausted: OOM when allocating a buffer of 205521156 bytes
[]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.
0 successful operations.
0 derived errors ignored.
Original stack trace for 'src_dst_opt_1/random_uniform_8/RandomUniform':
File "threading.py", line 884, in _bootstrap
File "threading.py", line 916, in _bootstrap_inner
File "threading.py", line 864, in run
File "F:\DeepFaceLab\_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
debug=debug)
File "F:\DeepFaceLab\_internal\DeepFaceLab\models\ModelBase.py", line 193, in __init__
self.on_initialize()
File "F:\DeepFaceLab\_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 327, in on_initialize
self.src_dst_opt.initialize_variables (self.src_dst_trainable_weights, vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
File "F:\DeepFaceLab\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 44, in initialize_variables
lr_rnds = [ nn.random_binomial( v.shape, p=self.lr_dropout, dtype=v.dtype) for v in trainable_weights ]
File "F:\DeepFaceLab\_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 44, in <listcomp>
lr_rnds = [ nn.random_binomial( v.shape, p=self.lr_dropout, dtype=v.dtype) for v in trainable_weights ]
File "F:\DeepFaceLab\_internal\DeepFaceLab\core\leras\ops\__init__.py", line 206, in random_binomial
random_ops.random_uniform(shape, dtype=tf.float16, seed=seed) < p,
File "F:\DeepFaceLab\_internal\python-3.6.8\lib\site-packages\tensorflow_core\python\ops\random_ops.py", line 245, in random_uniform
rnd = gen_random_ops.random_uniform(shape, dtype, seed=seed1, seed2=seed2)
File "F:\DeepFaceLab\_internal\python-3.6.8\lib\site-packages\tensorflow_core\python\ops\gen_random_ops.py", line 860, in random_uniform
name=name)
File "F:\DeepFaceLab\_internal\python-3.6.8\lib\site-packages\tensorflow_core\python\framework\op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "F:\DeepFaceLab\_internal\python-3.6.8\lib\site-packages\tensorflow_core\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "F:\DeepFaceLab\_internal\python-3.6.8\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3371, in create_op
attrs, op_def, compute_device) 签到领灵石 签到领灵石 新同学来报道 签到领灵石
页:
[1]
2